rough-cut-notes — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited rough-cut-notes (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Produces structured editorial notes from a rough cut description, identifying structural, pacing, and narrative issues and recommending specific solutions.
Required: A description of the rough cut: the sequence of scenes in order, approximate running time of each section, and what is in each section (interview subjects featured, what they say, observational footage, archival material, narration content) Optional: The film's intended running time; the broadcaster's brief or commissioning pitch; any specific concerns you already have about the cut; what previous feedback has been given (from editor, director, or broadcaster)
Tiered notes document. Sections: Structural Notes (things that affect the whole film), Sequence-Level Notes (specific scenes or sections), Pacing Notes (running time and energy issues), Narrative/Character Notes (story and subject issues), and Positive Observations (what is working). Each note: Issue Description | Impact | Suggested Fix. Notes are numbered for easy reference in conversation with an editor or director. Total length: 600–1000 words depending on cut complexity. Output ends with a "Next Step" note: the single highest-priority change to make before the next cut, the estimated runtime saving if pacing notes are followed, and whether a director-editor review session should be scheduled around the structural notes.
Rough cut description: A 74-minute rough cut (target 55 minutes) of a documentary about a community legal clinic that provides free immigration services. The film follows three clients — Miriam (asylum seeker from West Africa), Kwon (a young man navigating a visa appeal), and Claudia (long-time resident with suddenly threatened status) — and the two lawyers at the clinic, Sandra and Darius.
Sequence order and timings:
Director's existing concern: The film feels too long and the middle section loses momentum.
Rough Cut Notes — Immigration Legal Clinic Documentary Cut length: 74 minutes | Target: 55 minutes | Notes prepared: March 2026
Structural Notes
S1 — The film has four main characters but the structure treats them as three parallel stories rather than one. Impact: The film reads as three separate mini-documentaries housed inside one program. The lawyers (Sandra and Darius) do not become structurally significant until minute 50, by which point the viewer has been watching for almost an hour without fully understanding why we are at this clinic and not any other. Suggested fix: Move the Sandra and Darius sequence (currently 50–58 minutes) to approximately minute 15 — after the clinic introduction but before the first client case is developed. Establishing the lawyers' motivations and the clinic's particular ethos early gives every subsequent client scene a human anchor. This also creates the structural shape of: institution → clients → institution again at close, which is much stronger than: institution introduction → three client stories → institution reflection.
S2 — The 15-minute Miriam section (7:00–22:00) is structurally overweighted at the film's opening. Impact: Miriam's backstory is important and compelling, but 15 minutes of interview and archive before the film has established its legs means the viewer is in deep emotional debt before they understand the film's structure. This is why the middle section feels slow — the film spent its first act on depth rather than establishment. Suggested fix: Reduce the initial Miriam section to 6–8 minutes (the essential backstory beats only), hold her most emotionally complex interview material for after her hearing result (currently at 40–50 minutes), and build Kwon and Claudia's introductions earlier. Distribute the emotional weight more evenly.
Sequence-Level Notes
Seq1 — The waiting room footage (0:00–7:00) is the film's best observational material but is underused. Impact: The waiting room contains the film's argument in miniature — people from different countries, different circumstances, the same systemic vulnerability. It is currently used as ambient texture rather than narrative. Suggested fix: One of the three clients should be introduced in the waiting room before we know who they are — a face in the crowd that becomes, 10 minutes later, the center of the film. This requires a small re-edit of the opening sequence.
Seq2 — Kwon's courtroom footage (22:00–30:00) is the film's strongest observational sequence and is positioned too early. Impact: The courtroom footage has maximum power if the viewer is invested in Kwon — which requires more time with him in interview before his hearing is shown. Currently we watch the hearing before we know enough about him to care deeply. Suggested fix: Extend Kwon's introductory interview by 3–4 minutes before the courtroom sequence, or move the courtroom sequence to later in his arc.
Pacing Notes
P1 — The cut is 19 minutes over target. The following sections can absorb most of the trim without losing material content:
Total recoverable: approximately 11–12 minutes, leaving 7–8 minutes of structural re-editing work to reach the target.
Narrative and Character Notes
N1 — Claudia's outcome is the most ambiguous of the three, which is an editorial strength, but it needs a clearer setup. Currently we do not fully understand what Claudia's threatened status means practically — what happens to her life if her case fails. Add one specific detail in her introduction (where she has lived, what she would lose) to give the ambiguity of her outcome its full weight.
Positive Observations
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.